arXiv subjects

Jun Ma

Publications and source records attributed to Jun Ma.

At least 235 records · Page 13Linked to original sources

arXiv2024

SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning

We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal self-supervised learning is first presented to facilitate the unsupervised cross-modal homography estimation. The correlation-based homography estimation network and the consistent feature map projection are combined to form the learnable architecture of SCPNet, boosting the unsupervised learning framework. SCPNet is the first to achieve effective unsupervised homography estimation on the satellite-map image pair cross-modal dataset, GoogleMap, under [-32,+32] offset on a 128x128 image, leading the supervised approach MHN by 14.0% of mean average corner error (MACE). We further conduct extensive experiments on several cross-modal/spectral and manually-made inconsistent datasets, on which SCPNet achieves the state-of-the-art (SOTA) performance among unsupervised approaches, and owns 49.0%, 25.2%, 36.4%, and 10.7% lower MACEs than the supervised approach MHN. Source code is available at https://github.com/RM-Zhang/SCPNet.

cs.CV↗

arXiv2024

Compositions of the Hercules-Aquila Cloud and Virgo Over-density

Based on a sample of K giant from Large sky Area Multi-Object fiber Spectroscopic Telescope (LAMOST) Data Release 8 and a sample of RR Lyrae (RRL) from \textit{Gaia} Data Release 3, we investigate the compositions of the Hercules-Aquila Cloud (HAC) and Virgo Over-density (VOD) and their collective contribution to the tilt and triaxiality of the stellar halo ($r\,\textless\,40\,{\rm kpc}$) as well as two breaks at $\approx15\,{\rm kpc}$ and 30\,kpc. We apply the Gaussian mixture model (GMM) to divide the stellar halo into the isotropic component and the radially biased anisotropic component, namely Gaia-Sausage-Enceladus (GSE), and find that both HAC and VOD are dominated by the GSE debris stars with weights of $0.67^{+0.09}_{-0.07}$ and $0.57^{+0.07}_{-0.06}$, respectively. In addition, using the K giants with orbital parameters, we identify the member stars of known substructures, including GSE, Sagittarius (Sgr), Helmi Streams, Sequoia, Thamnos, Pontus, Wukong, and Metal-weak Thick Disk (MWTD), to probe the compositions of low-eccentricity stars in the HAC and VOD regions. In density fittings of the RRL sample, we note that the absence of HAC and VOD has a weak effect on the shape of halo. Finally, we find that the radially biased anisotropic halo contributes majorly to the stellar halo that can be modelled with a tilted triaxial ellipsoid and a doubly broken power law with breaking radii at $18.08^{+2.04}_{-3.22}\,{\rm kpc}$ and $33.03^{+1.30}_{-1.21}\,{\rm kpc}$. This has important significance for understanding the status of large diffuse over-densities in the Milky Way.

astro-ph.GA↗

arXiv2024

DIM: Dynamic Integration of Multimodal Entity Linking with Large Language Model

Our study delves into Multimodal Entity Linking, aligning the mention in multimodal information with entities in knowledge base. Existing methods are still facing challenges like ambiguous entity representations and limited image information utilization. Thus, we propose dynamic entity extraction using ChatGPT, which dynamically extracts entities and enhances datasets. We also propose a method: Dynamically Integrate Multimodal information with knowledge base (DIM), employing the capability of the Large Language Model (LLM) for visual understanding. The LLM, such as BLIP-2, extracts information relevant to entities in the image, which can facilitate improved extraction of entity features and linking them with the dynamic entity representations provided by ChatGPT. The experiments demonstrate that our proposed DIM method outperforms the majority of existing methods on the three original datasets, and achieves state-of-the-art (SOTA) on the dynamically enhanced datasets (Wiki+, Rich+, Diverse+). For reproducibility, our code and collected datasets are released on \url{https://github.com/season1blue/DIM}.

cs.CL↗

arXiv2024

QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge

Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable image segmentation. This variability not only reflects the inherent complexity and subjective nature of medical image interpretation but also directly impacts the development and evaluation of automated segmentation algorithms. Accurately modeling and quantifying this variability is essential for enhancing the robustness and clinical applicability of these algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ), which was organized in conjunction with International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020 and 2021. The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets. The large collection of images with multi-rater annotations features various modalities such as MRI and CT; various organs such as the brain, prostate, kidney, and pancreas; and different image dimensions 2D-vs-3D. A total of 24 teams submitted different solutions to the problem, combining various baseline models, Bayesian neural networks, and ensemble model techniques. The obtained results indicate the importance of the ensemble models, as well as the need for further research to develop efficient 3D methods for uncertainty quantification methods in 3D segmentation tasks.

eess.IV↗

arXiv2024

PTA: Enhancing Multimodal Sentiment Analysis through Pipelined Prediction and Translation-based Alignment

Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA methods use a joint prediction approach to identify aspects and sentiments simultaneously. However, we argue that joint models are not always superior. Our analysis shows that joint models struggle to align relevant text tokens with image patches, leading to misalignment and ineffective image utilization. In contrast, a pipeline framework first identifies aspects through MATE (Multimodal Aspect Term Extraction) and then aligns these aspects with image patches for sentiment classification (MASC: Multimodal Aspect-Oriented Sentiment Classification). This method is better suited for multimodal scenarios where effective image use is crucial. We present three key observations: (a) MATE and MASC have different feature requirements, with MATE focusing on token-level features and MASC on sequence-level features; (b) the aspect identified by MATE is crucial for effective image utilization; and (c) images play a trivial role in previous MABSA methods due to high noise. Based on these observations, we propose a pipeline framework that first predicts the aspect and then uses translation-based alignment (TBA) to enhance multimodal semantic consistency for better image utilization. Our method achieves state-of-the-art (SOTA) performance on widely used MABSA datasets Twitter-15 and Twitter-17. This demonstrates the effectiveness of the pipeline approach and its potential to provide valuable insights for future MABSA research. For reproducibility, the code and checkpoint will be released.

cs.CL↗

arXiv2024

Empirical Likelihood Covariate Adjustment for Regression Discontinuity Designs

This paper proposes a versatile covariate adjustment method that directly incorporates covariate balance in regression discontinuity (RD) designs. The new empirical entropy balancing method reweights the standard local polynomial RD estimator by using the entropy balancing weights that minimize the Kullback--Leibler divergence from the uniform weights while satisfying the covariate balance constraints. Our estimator can be formulated as an empirical likelihood estimator that efficiently incorporates the information from the covariate balance condition as correctly specified over-identifying moment restrictions, and thus has an asymptotic variance no larger than that of the standard estimator without covariates. We demystify the asymptotic efficiency gain of Calonico, Cattaneo, Farrell, and Titiunik (2019)'s regression-based covariate-adjusted estimator, as their estimator has the same asymptotic variance as ours. Further efficiency improvement from balancing over sieve spaces is possible if our entropy balancing weights are computed using stronger covariate balance constraints that are imposed on functions of covariates. We then show that our method enjoys favorable second-order properties from empirical likelihood estimation and inference: the estimator has a small (bounded) nonlinearity bias, and the likelihood ratio based confidence set admits a simple analytical correction that can be used to improve coverage accuracy. The coverage accuracy of our confidence set is robust against slight perturbation to the covariate balance condition, which may happen in cases such as data contamination and misspecified "unaffected" outcomes used as covariates. The proposed entropy balancing approach for covariate adjustment is applicable to other RD-related settings.

econ.EM↗

arXiv2024

MCGMapper: Light-Weight Incremental Structure from Motion and Visual Localization With Planar Markers and Camera Groups

Structure from Motion (SfM) and visual localization in indoor texture-less scenes and industrial scenarios present prevalent yet challenging research topics. Existing SfM methods designed for natural scenes typically yield low accuracy or map-building failures due to insufficient robust feature extraction in such settings. Visual markers, with their artificially designed features, can effectively address these issues. Nonetheless, existing marker-assisted SfM methods encounter problems like slow running speed and difficulties in convergence; and also, they are governed by the strong assumption of unique marker size. In this paper, we propose a novel SfM framework that utilizes planar markers and multiple cameras with known extrinsics to capture the surrounding environment and reconstruct the marker map. In our algorithm, the initial poses of markers and cameras are calculated with Perspective-n-Points (PnP) in the front-end, while bundle adjustment methods customized for markers and camera groups are designed in the back-end to optimize the 6-DOF pose directly. Our algorithm facilitates the reconstruction of large scenes with different marker sizes, and its accuracy and speed of map building are shown to surpass existing methods. Our approach is suitable for a wide range of scenarios, including laboratories, basements, warehouses, and other industrial settings. Furthermore, we incorporate representative scenarios into simulations and also supply our datasets with pose labels to address the scarcity of quantitative ground-truth datasets in this research field. The datasets and source code are available on GitHub.

cs.RO↗

arXiv2024

Spatiotemporal Receding Horizon Control with Proactive Interaction Towards Autonomous Driving in Dense Traffic

In dense traffic scenarios, ensuring safety while keeping high task performance for autonomous driving is a critical challenge. To address this problem, this paper proposes a computationally-efficient spatiotemporal receding horizon control (ST-RHC) scheme to generate a safe, dynamically feasible, energy-efficient trajectory in control space, where different driving tasks in dense traffic can be achieved with high accuracy and safety in real time. In particular, an embodied spatiotemporal safety barrier module considering proactive interactions is devised to mitigate the effects of inaccuracies resulting from the trajectory prediction of other vehicles. Subsequently, the motion planning and control problem is formulated as a constrained nonlinear optimization problem, which favorably facilitates the effective use of off-the-shelf optimization solvers in conjunction with multiple shooting. The effectiveness of the proposed ST-RHC scheme is demonstrated through comprehensive comparisons with state-of-the-art algorithms on synthetic and real-world traffic datasets under dense traffic, and the attendant outcome of superior performance in terms of accuracy, efficiency and safety is achieved.

cs.RO↗

arXiv2024

EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning

The diagnosis and treatment of chest diseases play a crucial role in maintaining human health. X-ray examination has become the most common clinical examination means due to its efficiency and cost-effectiveness. Artificial intelligence analysis methods for chest X-ray images are limited by insufficient annotation data and varying levels of annotation, resulting in weak generalization ability and difficulty in clinical dissemination. Here we present EVA-X, an innovative foundational model based on X-ray images with broad applicability to various chest disease detection tasks. EVA-X is the first X-ray image based self-supervised learning method capable of capturing both semantic and geometric information from unlabeled images for universal X-ray image representation. Through extensive experimentation, EVA-X has demonstrated exceptional performance in chest disease analysis and localization, becoming the first model capable of spanning over 20 different chest diseases and achieving leading results in over 11 different detection tasks in the medical field. Additionally, EVA-X significantly reduces the burden of data annotation in the medical AI field, showcasing strong potential in the domain of few-shot learning. The emergence of EVA-X will greatly propel the development and application of foundational medical models, bringing about revolutionary changes in future medical research and clinical practice. Our codes and models are available at: https://github.com/hustvl/EVA-X.

cs.CV↗

arXiv2024

Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Driving

Recent years have seen a growing research interest in applications of Deep Neural Networks (DNN) on autonomous vehicle technology. The trend started with perception and prediction a few years ago and it is gradually being applied to motion planning tasks. Despite the performance of networks improve over time, DNN planners inherit the natural drawbacks of Deep Learning. Learning-based planners have limitations in achieving perfect accuracy on the training dataset and network performance can be affected by out-of-distribution problem. In this paper, we propose FusionAssurance, a novel trajectory-based end-to-end driving fusion framework which combines physics-informed control for safety assurance. By incorporating Potential Field into Model Predictive Control, FusionAssurance is capable of navigating through scenarios that are not included in the training dataset and scenarios where neural network fail to generalize. The effectiveness of the approach is demonstrated by extensive experiments under various scenarios on the CARLA benchmark.

cs.RO↗

arXiv2024

Parallel Optimization with Hard Safety Constraints for Cooperative Planning of Connected Autonomous Vehicles

The development of connected autonomous vehicles (CAVs) facilitates the enhancement of traffic efficiency in complicated scenarios. In unsignalized roundabout scenarios, difficulties remain unsolved in developing an effective and efficient coordination strategy for CAVs. In this paper, we formulate the cooperative autonomous driving problem of CAVs in the roundabout scenario as a constrained optimal control problem, and propose a computationally-efficient parallel optimization framework to generate strategies for CAVs such that the travel efficiency is improved with hard safety guarantees. All constraints involved in the roundabout scenario are addressed appropriately with convex approximation, such that the convexity property of the reformulated optimization problem is exhibited. Then, a parallel optimization algorithm is presented to solve the reformulated optimization problem, where an embodied iterative nearest neighbor search strategy to determine the optimal passing sequence in the roundabout scenario. It is noteworthy that the travel efficiency in the roundabout scenario is enhanced and the computation burden is considerably alleviated with the innovation development. We also examine the proposed method in CARLA simulator and perform thorough comparisons with a rule-based baseline and the commonly used IPOPT optimization solver to demonstrate the effectiveness and efficiency of the proposed approach.

cs.RO↗

arXiv2024

DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking

Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire image as input may contain redundant information. (2)the insufficient utilization of entity-related information, such as attributes in images. (3)semantic inconsistency between the entity in knowledge base and its representation. To this end, we propose DWE+ for multimodal entity linking. DWE+ could capture finer semantics and dynamically maintain semantic consistency with entities. This is achieved by three aspects: (a)we introduce a method for extracting fine-grained image features by partitioning the image into multiple local objects. Then, hierarchical contrastive learning is used to further align semantics between coarse-grained information(text and image) and fine-grained (mention and visual objects). (b)we explore ways to extract visual attributes from images to enhance fusion feature such as facial features and identity. (c)we leverage Wikipedia and ChatGPT to capture the entity representation, achieving semantic enrichment from both static and dynamic perspectives, which better reflects the real-world entity semantics. Experiments on Wikimel, Richpedia, and Wikidiverse datasets demonstrate the effectiveness of DWE+ in improving MEL performance. Specifically, we optimize these datasets and achieve state-of-the-art performance on the enhanced datasets. The code and enhanced datasets are released on https://github.com/season1blue/DWET

cs.AI↗

arXiv2024

Segment Anything in Medical Images

Medical image segmentation is a critical component in clinical practice, facilitating accurate diagnosis, treatment planning, and disease monitoring. However, existing methods, often tailored to specific modalities or disease types, lack generalizability across the diverse spectrum of medical image segmentation tasks. Here we present MedSAM, a foundation model designed for bridging this gap by enabling universal medical image segmentation. The model is developed on a large-scale medical image dataset with 1,570,263 image-mask pairs, covering 10 imaging modalities and over 30 cancer types. We conduct a comprehensive evaluation on 86 internal validation tasks and 60 external validation tasks, demonstrating better accuracy and robustness than modality-wise specialist models. By delivering accurate and efficient segmentation across a wide spectrum of tasks, MedSAM holds significant potential to expedite the evolution of diagnostic tools and the personalization of treatment plans.

eess.IV↗

arXiv2024

The Multi-modality Cell Segmentation Challenge: Towards Universal Solutions

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimental settings. Here, we present a multi-modality cell segmentation benchmark, comprising over 1500 labeled images derived from more than 50 diverse biological experiments. The top participants developed a Transformer-based deep-learning algorithm that not only exceeds existing methods but can also be applied to diverse microscopy images across imaging platforms and tissue types without manual parameter adjustments. This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging.

eess.IV↗

arXiv2024

Generative Retrieval as Multi-Vector Dense Retrieval

Generative retrieval generates identifiers of relevant documents in an end-to-end manner using a sequence-to-sequence architecture for a given query. The relation between generative retrieval and other retrieval methods, especially those based on matching within dense retrieval models, is not yet fully comprehended. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. Accordingly, generative retrieval exhibits behavior analogous to hierarchical search within a tree index in dense retrieval when using hierarchical semantic identifiers. However, prior work focuses solely on the retrieval stage without considering the deep interactions within the decoder of generative retrieval. In this paper, we fill this gap by demonstrating that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document. Specifically, we examine the attention layer and prediction head of generative retrieval, revealing that generative retrieval can be understood as a special case of multi-vector dense retrieval. Both methods compute relevance as a sum of products of query and document vectors and an alignment matrix. We then explore how generative retrieval applies this framework, employing distinct strategies for computing document token vectors and the alignment matrix. We have conducted experiments to verify our conclusions and show that both paradigms exhibit commonalities of term matching in their alignment matrix.

cs.IR↗

arXiv2024

Arm-Constrained Curriculum Learning for Loco-Manipulation of the Wheel-Legged Robot

Incorporating a robotic manipulator into a wheel-legged robot enhances its agility and expands its potential for practical applications. However, the presence of potential instability and uncertainties presents additional challenges for control objectives. In this paper, we introduce an arm-constrained curriculum learning architecture to tackle the issues introduced by adding the manipulator. Firstly, we develop an arm-constrained reinforcement learning algorithm to ensure safety and stability in control performance. Additionally, to address discrepancies in reward settings between the arm and the base, we propose a reward-aware curriculum learning method. The policy is first trained in Isaac gym and transferred to the physical robot to do dynamic grasping tasks, including the door-opening task, fan-twitching task and the relay-baton-picking and following task. The results demonstrate that our proposed approach effectively controls the arm-equipped wheel-legged robot to master dynamic grasping skills, allowing it to chase and catch a moving object while in motion. Please refer to our website (https://acodedog.github.io/wheel-legged-loco-manipulation) for the code and supplemental videos.

cs.RO↗

arXiv2024

Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models

Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory requirement makes it challenging to deploy them on edge devices. In this study, we propose a light-weight quantization aware fine tuning technique using knowledge distillation (KD-QAT) to improve the performance of 4-bit weight quantized LLMs using commonly available datasets to realize a popular language use case, on device chat applications. To improve this paradigm of finetuning, as main contributions, we provide insights into stability of KD-QAT by empirically studying the gradient propagation during training to better understand the vulnerabilities of KD-QAT based approaches to low-bit quantization errors. Based on our insights, we propose ov-freeze, a simple technique to stabilize the KD-QAT process. Finally, we experiment with the popular 7B LLaMAv2-Chat model at 4-bit quantization level and demonstrate that ov-freeze results in near floating point precision performance, i.e., less than 0.7% loss of accuracy on Commonsense Reasoning benchmarks.

cs.LG↗

arXiv2024

Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation

Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amounts of lifelong user behavioral sequences have been generated. However, existing sequential recommender models often struggle to handle such lifelong sequences. The primary challenges stem from computational complexity and the ability to capture long-range dependencies within the sequence. Recently, a state space model featuring a selective mechanism (i.e., Mamba) has emerged. In this work, we investigate the performance of Mamba for lifelong sequential recommendation (i.e., length>=2k). More specifically, we leverage the Mamba block to model lifelong user sequences selectively. We conduct extensive experiments to evaluate the performance of representative sequential recommendation models in the setting of lifelong sequences. Experiments on two real-world datasets demonstrate the superiority of Mamba. We found that RecMamba achieves performance comparable to the representative model while significantly reducing training duration by approximately 70% and memory costs by 80%. Codes and data are available at \url{https://github.com/nancheng58/RecMamba}.

cs.IR↗